Agent Builder — UI Wireframe

Config Studio (left) + Pipeline Canvas + Trace Panel (right)

Config Studio agent-builder v1
Agents
Tools
Models
Prompts
Memory
Guardrails
Create New Agent
An agent is a reusable AI worker. It references a model, tools, memory and guardrails.

Agent Name
Description shown to users in the pipeline builder
Model reference from Models tab
Tools references from Tools tab
web_search
code_exec
http_request
+ Add Tool
System Prompt reference from Prompts tab
Memory from Memory tab
Guardrails from Guardrails tab
Will save as agent:researcher-agent:v1
Create New Tool
A tool is something the LLM can call mid-response. The description tells the LLM when to use it.

Tool Name
Description the LLM reads this to decide when to call this tool
Type
Endpoint URL
Auth Type
Input Schema what parameters the LLM must pass
Timeout (ms)
Will save as tool:web_search:v1
Create Model Config
A reusable wrapper around an LLM provider. Pin temperature and token limits once, reference everywhere.

Config Name
Provider
Model
Temperature
Max Tokens
Top-p
API Key Secret pulled from Vault at runtime, never stored here
Stream responses
Will save as model:gpt-4o-precise:v1
Create System Prompt
Keep prompts separate from agents so you can update them in one place without touching the agent config.

Prompt Name
Prompt Text
Variables dynamic values injected at runtime
{{user_name}}
{{today_date}}
+ Add Variable
Will save as prompt:researcher-base:v1
Create Memory Config
Defines how an agent remembers conversation history across turns. Referenced by agents, applied by the runtime.

Config Name
Memory Type
Window Size last N messages to keep
TTL (hours) expire after inactivity
Scope
Storage Backend
At runtime: worker loads last 10 messages from Redis → injects into LLM prompt → saves updated history back to Redis after response.
Will save as memory:sliding-10:v1
Create Guardrail
Wraps an agent with input and output rules. Checked automatically before and after every LLM call.

Guardrail Name
Input Rules checked before the agent sees the message
Block prompt injection attemptsINPUT
Reject messages > 4000 charsINPUT
Block off-topic requests (finance only)BLOCK
+ Add Input Rule
Output Rules checked before the response leaves the agent
Redact phone numbers and emailsOUTPUT
Block responses > 2000 tokensOUTPUT
Never reveal system promptBLOCK
+ Add Output Rule
Log all guardrail violations
Will save as guardrail:no-pii:v1
Pipeline Canvas
Zoom
Save
▶ Run
+ Agent
+ HITL
+ Condition
ENTRY
Pipeline Input
AGENT
Researcher
agent:researcher:v2
🔧 web_search
🧠 sliding-10
🛡 no-pii
AGENT
Fact Check
agent:factcheck:v1
🔧 web_search
🛡 no-pii
👤
HITL Review
awaiting approval
⏸ checkpointed
AGENT
Writer
agent:writer:v1
🛡 no-pii
AGENT
Publisher
agent:publisher:v1
🔧 http_post
EXIT
Pipeline Output
Live Trace
Running — waiting for HITL approval
00:00.1researcher:v2 started
00:01.4tool: web_search("AI trends 2025") called
00:03.2tool: web_search returned 8 results
00:04.8researcher:v2 completed (tokens: 1,240)
00:05.0factcheck:v1 completed (tokens: 880)
00:05.1state checkpointed → Redis + Postgres
00:05.2HITL node reached — pipeline paused, awaiting human approval
·writer:v1 — waiting
·publisher:v1 — waiting